06573d7f67
online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered
2024-04-10 11:34:01 +00:00
e6c6c2367f
Merge remote-tracking branch 'upstream/user/rcadene/2024_03_31_remove_torchrl' into refactor_act
2024-04-09 08:36:28 +01:00
6902e01db0
tests are passing for aloha/act policies, removes abstract policy
2024-04-09 03:28:56 +00:00
73dfa3c8e3
tests for tdmpc and diffusion policy are passing
2024-04-09 02:50:32 +00:00
9c96349926
Merge remote-tracking branch 'upstream/user/rcadene/2024_03_31_remove_torchrl' into refactor_act
2024-04-08 15:44:00 +01:00
70aaf1c4cb
test_datasets.py are passing!
2024-04-08 14:16:57 +00:00
0b4c42f4ff
typos
2024-04-08 14:59:37 +01:00
62b18a7607
Add type hints
2024-04-08 14:51:45 +01:00
86365adf9f
revision
2024-04-08 14:44:46 +01:00
863f28ffd8
ready for review
2024-04-08 13:10:19 +01:00
1bab4a1dd5
Eval reproduction works with gym_aloha
2024-04-08 10:23:26 +01:00
e982c732f1
Merge remote-tracking branch 'Cadene/user/rcadene/2024_03_31_remove_torchrl' into refactor_act_remove_torchrl
2024-04-08 09:25:45 +01:00
4371a5570d
Remove latency, tdmpc policy passes tests (TODO: make it work with online RL)
2024-04-07 16:01:22 +00:00
8d2463f45b
backup wip
2024-04-05 18:46:30 +01:00
ab2286025b
Merge remote-tracking branch 'Cadene/user/rcadene/2024_03_31_remove_torchrl' into refactor_act_remove_torchrl
2024-04-05 18:06:00 +01:00
1e71196fe3
backup wip
2024-04-05 17:38:29 +01:00
f56b1a0e16
WIP tdmpc
2024-04-05 13:40:31 +00:00
0b8d27ff2c
Merge remote-tracking branch 'Cadene/user/rcadene/2024_03_31_remove_torchrl' into refactor_act_remove_torchrl
2024-04-05 12:48:11 +01:00
c17dffe944
policies/utils.py
2024-04-05 11:47:15 +00:00
8ba88ba250
Merge remote-tracking branch 'Cadene/user/rcadene/2024_03_31_remove_torchrl' into refactor_act_remove_torchrl
2024-04-05 12:34:14 +01:00
a420714ee4
fix: action_is_pad was missing in compute_loss
2024-04-05 11:33:39 +00:00
9d77f5773d
Merge remote-tracking branch 'Cadene/user/rcadene/2024_03_31_remove_torchrl' into refactor_act_remove_torchrl
2024-04-05 11:41:11 +01:00
edb125b351
backup wip
2024-04-05 11:03:28 +01:00
5af00d0c1e
fix train.py, stats, eval.py (training is running)
2024-04-05 09:31:39 +00:00
3a4dfa82fe
backup wip
2024-04-04 18:34:41 +01:00
1cdfbc8b52
WIP
...
WIP
WIP train.py works, loss going down
WIP eval.py
Fix
WIP (eval running, TODO: verify results reproduced)
Eval works! (testing reproducibility)
WIP
pretrained model pusht reproduces same results as torchrl
pretrained model pusht reproduces same results as torchrl
Remove AbstractPolicy, Move all queues in select_action
WIP test_datasets passed (TODO: re-enable NormalizeTransform)
2024-04-04 15:31:03 +00:00
278336a39a
backup wip
2024-04-03 19:23:22 +01:00
110ac5ffa1
backup wip
2024-04-03 14:21:07 +01:00
65ef8c30d0
backup wip
2024-04-02 19:13:49 +01:00
2b928eedd4
backup wip
2024-04-02 19:11:53 +01:00
1a1308d62f
fix environment seeding
...
add fixes for reproducibility
only try to start env if it is closed
revision
fix normalization and data type
Improve README
Improve README
Tests are passing, Eval pretrained model works, Add gif
Update gif
Update gif
Update gif
Update gif
Update README
Update README
update minor
Update README.md
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Update README.md
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Address suggestions
Update thumbnail + stats
Update thumbnail + stats
Update README.md
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
Add more comments
Add test_examples.py
2024-03-26 10:10:43 +00:00
bcfdba109f
Update pre-commit & run on all files
2024-03-25 17:29:35 +01:00
72d3c3120b
Merge remote-tracking branch 'upstream/main' into fix_pusht_diffusion
2024-03-21 10:20:52 +00:00
acf1174447
ready for review
2024-03-21 10:18:50 +00:00
4631d36c05
Add get_safe_torch_device in policies
2024-03-20 18:38:55 +01:00
d323993569
backup wip
2024-03-20 15:01:27 +00:00
4b7ec81dde
remove abstracmethods, fix online training
2024-03-20 14:49:41 +00:00
32e3f71dd1
backup wip
2024-03-20 09:49:16 +00:00
5332766a82
revision
2024-03-20 09:45:45 +00:00
4f1955edfd
Clear action queue when environment is reset
2024-03-20 08:31:06 +00:00
896a11f60e
backup wip
2024-03-19 18:50:04 +00:00
ea17f4ce50
backup wip
2024-03-19 16:02:09 +00:00
88347965c2
revert dp changes, make act and tdmpc batch friendly
2024-03-18 19:18:21 +00:00
a222c88c99
Merge branch 'user/alexander-soare/train_pusht' into user/alexander-soare/multistep_policy_and_serial_env
2024-03-14 16:06:21 +00:00
ba91976944
wip: still needs batch logic for act and tdmp
2024-03-14 15:24:10 +00:00
98484ac68e
ready for review
2024-03-12 21:59:01 +00:00
9512d1d2f3
Merge branch 'main' into user/alexander-soare/train_pusht
2024-03-12 19:41:27 +00:00
9d002032d1
Add Aloha env and ACT policy
...
WIP Aloha env tests pass
Rendering works (fps look fast tho? TODO action bounding is too wide [-1,1])
Update README
Copy past from act repo
Remove download.py add a WIP for Simxarm
Remove download.py add a WIP for Simxarm
Add act yaml (TODO: try train.py)
Training can runs (TODO: eval)
Add tasks without end_effector that are compatible with dataset, Eval can run (TODO: training and pretrained model)
Add AbstractEnv, Refactor AlohaEnv, Add rendering_hook in env, Minor modifications, (TODO: Refactor Pusht and Simxarm)
poetry lock
fix bug in compute_stats for action normalization
fix more bugs in normalization
fix training
fix import
PushtEnv inheriates AbstractEnv, Improve factory Normalization
Add _make_env to EnvAbstract
Add call_rendering_hooks to pusht env
SimxarmEnv inherites from AbstractEnv (NOT TESTED)
Add aloha tests artifacts + update pusht stats
fix image normalization: before env was in [0,1] but dataset in [0,255], and now both in [0,255]
Small fix on simxarm
Add next to obs
Add top camera to Aloha env (TODO: make it compatible with set of cameras)
Add top camera to Aloha env (TODO: make it compatible with set of cameras)
2024-03-12 10:27:48 +00:00
87fcc536f9
wip - still need to verify full training run
2024-03-11 18:45:21 +00:00
2a01487494
early training loss as expected
2024-03-11 13:34:04 +00:00
134009f337
Remove init files
2024-03-10 16:38:49 +01:00
6c867d78ef
Integrate pusht env from diffusion
2024-03-10 16:33:03 +01:00
302b78962c
Integrate diffusion policy
2024-03-10 15:31:17 +01:00
59397fb44a
Move tdmpc files
2024-03-09 18:44:36 +01:00
a6d353c419
Fix
2024-03-05 17:00:17 +01:00
e990f3e148
Merge pull request #6 from Cadene/user/rcadene/2024_03_04_diffusion
...
Make diffusion work
2024-03-04 18:30:40 +01:00
cfc304e870
Refactor env queue, Training diffusion works (Still not converging)
2024-03-04 11:00:51 +00:00
fddd9f0311
Add possibility for the policy to provide a sequence of actions to the env
2024-03-03 14:02:24 +00:00
0f2fa4d9ef
Add obs queue to pusht, Set n_obs_steps=2 for diffusion (Not fully tested)
2024-03-03 13:21:31 +00:00
b33ec5a630
Add run on cpu-only compatibility
2024-03-03 12:47:26 +01:00
80785f8d0e
Small fix, Refactor diffusion, Diffusion runs (TODO: remove normalization in diffusion)
2024-03-02 17:04:39 +00:00
45b4ecb727
pre-commit run -a
2024-03-02 15:58:21 +00:00
1ae6205269
Add Normalize, non_blocking=True in tdmpc, tdmpc run (TODO: diffusion)
2024-03-02 15:53:29 +00:00
ca948c1e5b
fix zip strict=False
2024-03-01 00:45:23 +00:00
ae050d2e94
Solve conflicts + pre-commit run -a
2024-02-29 23:31:32 +00:00
0b9027f05e
Clean logging, Refactor
2024-02-29 23:21:27 +00:00
2c05b75f45
Fixes for PR #3
2024-02-29 21:46:41 +01:00
7e024fdce6
Ran pre-commit run --all-files
2024-02-29 13:37:48 +01:00
ac90b9c3ee
Fix diffusion (rm transpose), Add prefetch
2024-02-28 17:45:01 +00:00
cf5063e50e
Add diffusion policy (train and eval works, TODO: reproduce results)
2024-02-28 15:21:42 +00:00
21670dce90
Refactor train, eval_policy, logger, Add diffusion.yaml (WIP)
2024-02-26 01:10:09 +00:00
b16c334825
Refactor configs to have env in seperate yaml + Fix training
2024-02-25 17:42:47 +00:00
e765e26b0b
Sanitize cfg.policy, Fix skip_frame pusht.yaml
2024-02-25 11:09:02 +00:00
598bb496b0
Add policies/factory, Add test, Add _self_ in config
2024-02-25 10:50:23 +00:00
Cadene
Alexander Soare
Simon Alibert